Slope reliability analysis using surrogate models via new support vector machines with swarm intelligence

A new reliability-based design optimization (RBDO) method based on support vector machines (SVM) and the Most Probable Point (MPP) is proposed in this work. SVM is used to create a surrogate model of the limit-state function at the MPP with the gradient information in the reliability analysis. This guarantees that the surrogate model not only passes through the MPP but also is tangent to the limit-state function at the MPP. Then, importance sampling (IS) is used to calculate the probability of failure based on the surrogate model. This treatment significantly improves the accuracy of reliability analysis. For RBDO, the Sequential Optimization and Reliability Assessment (SORA) is employed as well, which decouples deterministic optimization from the reliability analysis. The improved SVM-based reliability analysis is used to amend the error from linear approximation for limit-state function in SORA. A mathematical example and a simplified aircraft wing design demonstrate that the improved SVM-based reliability analysis is more accurate than FORM and needs less training points than the Monte Carlo simulation and that the proposed optimization strategy is efficient.

Download Full-text

Adaptive Learning for Reliability Analysis using Support Vector Machines

10.3850/978-981-18-2016-8_093-cd ◽

2021 ◽

Author(s):

Nick Pepper ◽

Luis Crespo ◽

Francesco Montomoli

Keyword(s):

Support Vector Machines ◽

Reliability Analysis ◽

Adaptive Learning ◽

Support Vector ◽

Vector Machines

Download Full-text

A Least Square Support Vector Machine Approach Based on Uniform Design Method for Structural Reliability Analysis

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.163-167.3348 ◽

2010 ◽

Vol 163-167 ◽

pp. 3348-3353 ◽

Cited By ~ 2

Author(s):

Xiao Lin Yu ◽

Heng Bin Zheng ◽

Quan Sheng Yan ◽

Wei Li

Keyword(s):

Support Vector Machines ◽

Reliability Analysis ◽

Response Surface ◽

Design Method ◽

Uniform Design ◽

Support Vector ◽

Complex Structures ◽

Reliability Method ◽

Vector Machines ◽

Uniform Design Method

Since the performance functions of large complex structures can not be expressed explicitly in the process of reliability analysis, support vector machines (SVM) with good ability of generalization are used as the response surface function based on the small training samples. The uniform design method was adopted in selecting the training data. The least support vector machines (LS-SVM) were used to find the support vectors. The limit state function was expressed by the LS-SVM regression. Reliability analysis was then performed by the usual reliability method (e.g., the first-order reliability method, the second-order reliability method or Monte Carlo) on the response surface. The results of calculations of numerical examples and a typical cable-stayed bridge show that LS-SVM using the uniform design method can well approximate the real response of complex structures which has a good efficiency and accuracy and can be applied in complex structures.

Download Full-text